def build_model(self):
if self.args.search_mode == "macro":
search_space_cls = MacroSearchSpace()
self.search_space = search_space_cls.get_search_space()
self.action_list = search_space_cls.generate_action_list(
self.args.layers_of_child_model)
# build RNN controller
if self.args.dataset in ["cora", "citeseer", "pubmed"]:
# implements based on dgl
self.submodel_manager = CitationGNNManager(self.args)
if self.args.dataset in ["Cora", "Citeseer", "Pubmed",
"CS", "Physics", "Computers", "Photo"]:
# implements based on pyg
self.submodel_manager = GeoCitationManager(self.args)
print("Search space:")
print(self.search_space)
print("Generated Action List: ")
print(self.action_list)
def build_model(self):
self.args.share_param = False
self.with_retrain = True
self.args.shared_initial_step = 0
if self.args.search_mode == "macro":
# generate model description in macro way (generate entire network description)
from graphnas.search_space import MacroSearchSpace
search_space_cls = MacroSearchSpace()
self.search_space = search_space_cls.get_search_space()
# layers_of_child_model is 2
self.action_list = search_space_cls.generate_action_list(
self.args.layers_of_child_model)
# build RNN controller
from graphnas.graphnas_controller import SimpleNASController
self.controller = SimpleNASController(
self.args,
action_list=self.action_list,
search_space=self.search_space,
cuda=self.args.cuda)
if self.args.dataset in ["cora", "citeseer", "pubmed"]:
# implements based on dgl
self.submodel_manager = CitationGNNManager(self.args)
if self.args.dataset in ["Cora", "Citeseer", "Pubmed"]:
# implements based on pyg
self.submodel_manager = GeoCitationManager(self.args)
if self.args.search_mode == "micro":
self.args.format = "micro"
self.args.predict_hyper = True
if not hasattr(self.args, "num_of_cell"):
self.args.num_of_cell = 2
from graphnas_variants.micro_graphnas.micro_search_space import IncrementSearchSpace
search_space_cls = IncrementSearchSpace()
search_space = search_space_cls.get_search_space()
from graphnas.graphnas_controller import SimpleNASController
from graphnas_variants.micro_graphnas.micro_model_manager import MicroCitationManager
self.submodel_manager = MicroCitationManager(self.args)
self.search_space = search_space
action_list = search_space_cls.generate_action_list(
cell=self.args.num_of_cell)
if hasattr(self.args, "predict_hyper") and self.args.predict_hyper:
self.action_list = action_list + [
"learning_rate", "dropout", "weight_decay", "hidden_unit"
]
else:
self.action_list = action_list
self.controller = SimpleNASController(
self.args,
action_list=self.action_list,
search_space=self.search_space,
cuda=self.args.cuda)
if self.cuda:
self.controller.cuda()
if self.cuda:
self.controller.cuda()
def build_model(self):
self.args.share_param = False
self.with_retrain = True
self.args.shared_initial_step = 0
if self.args.search_mode == "macro":
# generate model description in macro way (generate entire network description)
from graphnas.search_space import MacroSearchSpace
search_space_cls = MacroSearchSpace()
self.search_space = search_space_cls.get_search_space()
self.action_list = search_space_cls.generate_action_list(self.args.layers_of_child_model)
# build RNN controller
from graphnas.graphnas_controller import SimpleNASController
self.controller = SimpleNASController(self.args, action_list=self.action_list,
search_space=self.search_space,
cuda=self.args.cuda)
if self.args.dataset in ["Cora", "Citeseer", "Pubmed"]:
# implements based on pyg
self.submodel_manager = GeoCitationManager(self.args)
if self.cuda:
self.controller.cuda()
def build_model(self):
if self.args.search_mode == "macro":
# generate model description in macro way
# (generate entire network description)
search_space_cls = MacroSearchSpace()
self.search_space = search_space_cls.get_search_space()
self.action_list = search_space_cls.generate_action_list(
self.args.layers_of_child_model)
# build RNN controller
if self.args.dataset in ["cora", "citeseer", "pubmed"]:
# implements based on dgl
self.submodel_manager = CitationGNNManager(self.args)
if self.args.dataset in [
"Cora", "Citeseer", "Pubmed", "CS", "Physics", "Computers",
"Photo"
]:
# implements based on pyg
self.submodel_manager = GeoCitationManager(self.args)
if self.args.search_mode == "micro":
self.args.format = "micro"
self.args.predict_hyper = True
if not hasattr(self.args, "num_of_cell"):
self.args.num_of_cell = 2
search_space_cls = IncrementSearchSpace()
search_space = search_space_cls.get_search_space()
self.submodel_manager = MicroCitationManager(self.args)
self.search_space = search_space
action_list = search_space_cls.generate_action_list(
cell=self.args.num_of_cell)
if hasattr(self.args, "predict_hyper") and self.args.predict_hyper:
self.action_list = action_list + [
"learning_rate", "dropout", "weight_decay", "hidden_unit"
]
else:
self.action_list = action_list
print("Search space:")
print(self.search_space)
print("Generated Action List: ")
print(self.action_list)
def fitness_func(solution, solution_idx):
args = build_args()
if args.cuda and not torch.cuda.is_available(): # cuda is not available
args.cuda = False
torch.manual_seed(args.random_seed)
if args.cuda:
torch.cuda.manual_seed(args.random_seed)
utils.makedirs(args.dataset)
global trnr
search_space = MacroSearchSpace().search_space
gnn = []
gnn.append(search_space['attention_type'][int(solution[0])])
gnn.append(search_space['aggregator_type'][int(solution[1])])
gnn.append(search_space['activate_function'][int(solution[2])])
gnn.append(int(solution[3]))
gnn.append(int(solution[4]))
gnn.append(search_space['attention_type'][int(solution[5])])
gnn.append(search_space['aggregator_type'][int(solution[6])])
gnn.append(search_space['activate_function'][int(solution[7])])
gnn.append(int(solution[8]))
gnn.append(6)
fitness = trnr.genetic_get_reward(gnn)[1]
return fitness